Incorporating AI into your Workflow

A Practical Guide for Economists

AEDE 8895

The Ohio State University

Part I

AI in Your Research

Think, Pair, Share

For the following use cases, discuss whether you think AI is appropriate to use as part of your research:

  • Developing research questions/ideas
  • Coding
  • Theoretical modeling and derivations
  • Editing
  • Writing
  • Summarizing (post-publication)

Let’s Get More Specific!

Is the following use of AI appropriate?

You use AI to rewrite paragraphs you’ve already written to make them sound more professional and improve grammar.

Is the following use of AI appropriate?

You ask AI to write code to merge two datasets and run a standard regression based on your natural language instructions. You check the code and it seems correct.

Is the following use of AI appropriate?

You ask AI to “summarize the top 10 most influential papers on [X].” You use this summary to develop your literature review in a paper.

Is the following use of AI appropriate?

You ask AI to propose three novel research questions based on the gap in the literature between Paper X and Paper Y. You choose one and it becomes the basis for your paper for your dissertation.

Is the following use of AI appropriate?

Your advisor asks you to review a paper for the AJAE. You upload the paper to AI and ask it to review the paper. You use these as the primary critiques of the paper.

Part II

My Thoughts on AI

Two observations and a question

  1. AI has made it virtually costless to write grammatically correct prose with no spelling errors.

  2. AI has given everyone a (near) Ph.D.-level coding assistant and data analyst.



What is the equilibrium response for economics job market candidates?

A few thoughts on the job market

  • The average quality (and expectations) of a JMP will be higher every year

  • Expectations for more complex analyses will increase

  • Bad writing will likely become a very bad signal

  • Boring/generic writing will signal overreliance on AI

  • Interpersonal skills will become more critical

Finding the balance

1. Learn the fundamentals — You can’t evaluate code you don’t understand. AI will confidently give you wrong answers—you need to catch them. Think of AI as a fast RA who occasionally hallucinates.


2. But don’t fall behind — Your peers are using these tools. The productivity gap compounds quickly. “I prefer the old way” is not a competitive strategy.


3. The old system was imperfect — Research errors happened before AI—and were caught late or not at all. Better workflows + AI review can catch errors earlier.

Finding the balance



The goal isn’t “AI vs. no AI”—it’s building systems that make research more robust, better, and more replicable.

Part III

Building Your Stack

1. Use a cloud platform + clear folder structure

Work from OneDrive, Dropbox, or Google Drive—not your local machine alone.

A consistent folder structure makes AI tools more effective because they can understand your project organization.

project-folder/
├── data/
│   ├── raw/
│   └── clean/
├── code/
│   ├── 01-clean.R
│   ├── 02-analysis.R
│   └── 03-figures.R
├── output/
├── paper/
└── README.md

2. Use Git/GitHub for version control

Why Git?

  • Track every change to your code
  • Revert to any previous version
  • See exactly what changed and when
  • Collaborate without overwriting

Why GitHub?

  • Cloud backup of your code history
  • Share and collaborate easily
  • AI tools integrate directly with repos
  • Replication packages ready to share

2. Use Git/GitHub for version control

No more analysis_v3_final_FINAL2.R — Git tracks it all.


git diff analysis.R
- model <- lm(y ~ x1 + x2, data = df)
+ model <- lm(y ~ x1 + x2 + x1:x2, data = df)  # added interaction


Confused on how to set up Git and GitHub? Ask AI!

3. Use AI coding tools: Claude Code vs. Cursor


Claude Code

What: Terminal-based, agentic coding assistant

Best for: Data analysis workflows, file operations & project setup, autonomous multi-step tasks, Git integration

Runs from command line

Cursor

What: AI-powered code editor

Best for: Iterative code editing, larger software projects, inline suggestions while typing, tab completion on steroids

4. Write papers in Overleaf + GitHub

Overleaf = collaborative LaTeX editing in the browser

GitHub sync = version control for your paper


The workflow:

Code → Figures & Tables → GitHub Repo → Overleaf Paper


One integrated system: Code changes automatically flow through to your paper.

Cautions & pitfalls

  1. AI will make errors and add analyses/code you didn’t ask it to — It will confidently change code that generates plausible-looking results but be completely wrong.

  2. Don’t let AI do your economic thinking — It’s a tool, not a co-author. Identification, intuition, and interpretation are yours.

  3. Always test AI-generated code — Run it. Check edge cases. Verify results make sense.

  4. Be thoughtful about sensitive data — Know what data you’re sending to AI services.

More resources

Resource Description
Kevin Bryan’s “Tech Stack” Comprehensive guide to modern research tools for economists
Fernández-Villaverde’s Git Tutorial Detailed Git tutorial for academic research
Claude Code Docs Official documentation for Claude’s coding assistant
Cursor AI-first code editor built on VS Code

Part IV

Live Demonstration

Questions?

Gabriel Lade

C. William Swank Chair in Rural-Urban Policy

Department of Agricultural, Environmental, and Development Economics

The Ohio State University